Trends and Keyword Networks in Machine Learning-Based Click Fraud Detection Research

Abstract

The rapid advancement of the digital economy has significantly increased the use of online advertising while concurrently giving rise to critical challenges, particularly in the form of click fraud”a manipulative act that harms advertisers by generating fraudulent clicks on digital advertisements. As click fraud attack patterns grow increasingly complex, machine learning (ML)-based research has emerged as a principal approach for detecting and mitigating these threats. This study aims to map the research landscape of ML-based click fraud detection through a bibliometric analysis to identify publication trends, patterns of international and institutional collaboration, and key thematic domains within this field. Employing a bibliometric methodology, the study analyzed 61 publications retrieved from Dimensions.ai spanning the years 2015–2024. The data were collected, refined using OpenRefine, and visualized with VOSviewer to examine keyword co-occurrences and research trends. The findings reveal a marked increase in publication volume since 2019, with dominant contributions from India, China, Saudi Arabia, and the United States. Furthermore, four principal research clusters were identified: cybersecurity, the relationship between click fraud and the digital advertising industry, dataset processing and evaluation techniques, and the development of ML-based detection systems. Each cluster offers practical contributions in areas such as system protection strategies, ad budget optimization, improved detection accuracy, and the development of scalable, real-time detection solutions. Recent trends highlight growing scholarly interest in model performance evaluation and the challenges posed by class imbalance (class skewness). This study concludes that more effective data management and the development of adaptive ML models capable of addressing evolving attack patterns are pivotal for future research. By providing a clearer mapping of current trends, this study aims to support the scientific community in developing more accurate and efficient click fraud detection strategies, thereby strengthening the integrity of the global digital advertising ecosystem.